Cloudinary
MCP server by Cloudinary
Upload, search, organize and transform images, videos and files in your Cloudinary media library, and generate images with AI.
Connect to Cloudinary
Cloudinary needs sign-in. Connect with its own URL:
Your client opens Cloudinary’s sign-in the first time you use it. The token stays between your client and Cloudinary.
Share this server
Opens this page, with the URL and setup steps.
mcp.tc/i/cloudinaryAbout
Connects to the asset management API of a Cloudinary product environment. You can upload assets from local paths, URLs or data URIs, list and search images, videos and raw files, manage tags, context and structured metadata, organize folders, apply transformations, and generate images from text or reference images.
Runs as a hosted streamable HTTP endpoint with OAuth sign-in by default. Header authentication also works with a cloudinary-url header or the cloudinary-cloud-name, cloudinary-api-key and cloudinary-api-secret headers. A local npm package, @cloudinary/asset-management-mcp, is available and needs the same credentials as environment variables.
What you can do
- Upload images, videos and raw files from paths, URLs or data URIs
- Search assets with queries or by visual similarity
- Add, remove or replace tags and metadata on many assets
- Create, move and delete folders in the media library
- Apply transformations to existing assets
- Generate images from text prompts or reference images
- Create ZIP or TGZ archives of assets
- Check account usage and credits
Tools 44
upload-assetUpload images, videos or raw files from file paths, URLs or base64 data URIs.
asset-renameChange an asset's public ID and optionally other metadata.
generate-archiveCreate a ZIP or TGZ archive containing a set of assets.
download-asset-backupDownload a backup copy of an asset.
delete-assetDelete an asset by its asset ID.
list-imagesList image assets, filtered by tags, prefix or public IDs.
list-videosList video assets, filtered by tags, prefix or public IDs.
list-filesList raw assets, filtered by tags, prefix or public IDs.
get-asset-detailsReturn the details of one asset by asset ID.
asset-updateUpdate an asset's metadata, tags and other attributes by asset ID.
list-tagsList tags applied to assets of a given type.
delete-derived-assetsDelete derived resources by derived resource ID.
Show 32 more tools
manage-asset-tagsAdd, remove or replace tags on multiple assets by public ID.
manage-asset-contextAdd or clear contextual metadata on multiple assets.
manage-asset-metadataSet structured metadata values on multiple assets.
get-usage-detailsReport storage, credits, bandwidth, requests and add-on usage.
create-asset-relationsRelate an asset to other assets by asset ID.
delete-asset-relationsRemove relations between an asset and other assets.
move-folderRename or move a folder with all its assets.
create-folderCreate a new empty folder at a given path.
delete-folderDelete a folder and the assets within it.
search-foldersFind folders matching a search expression.
search-assetsSearch assets with a Lucene-like query over attributes, dates and metadata.
visual-search-assetsFind images by visual similarity to a URL, asset ID or text description.
generate-imageGenerate an image from a text prompt using AI models.
generate-image-from-imagesGenerate or edit an image guided by reference images and a prompt.
get-generation-taskGet the status of an image generation task.
generate-video-from-imageCreate a video generation job Submits an image and prompt for video generation and returns a job you can poll for the result.
get-video-generation-jobPoll a video generation job Returns the current status of a generation job.
list-collectionsList collections Returns the collections the caller may read, most-recently-updated first by default (`updated_at desc`).
create-collectionCreate a collection Creates a collection under the given product environment and makes the caller the owner.
get-collectionGet a collection Returns a single collection by its external ID.
update-collectionUpdate a collection Updates a collection's name, description, and (for dynamic collections) configuration.
delete-collectionDelete a collection Deletes a collection.
list-collection-assetsList a collection's assets Returns the assets in a collection, newest first by default.
add-collection-assetsAdd assets to a collection Adds assets to an existing collection.
remove-collection-assetsRemove assets from a collection Removes the specified assets from an existing collection.
publish-collectionPublish a collection Creates a shareable public page for the collection and returns its URL.
list-collection-public-pagesList a collection's public pages Returns the public pages (shareable links) that have been created for the collection.
get-collection-public-pageGet a public page Returns a single public page of a collection by its external ID.
update-collection-public-pageUpdate a public page Updates the settings of a collection's public page and returns the updated page.
unpublish-collection-public-pageUnpublish a collection's public page Deletes a collection's public page so it's no longer shareable.
get-tx-referenceFetch Cloudinary transformation documentation before building transformations.
transform-assetCreate derived transformations of existing assets using eager transformations.
From the package’s own manifest, not a live connection, on 17 Nov 2026.
Example prompts
Upload this local image to Cloudinary and tag it summer-campaign
Find all videos tagged product-demo uploaded this month
Generate an image of a red bicycle on a beach and check the task status
Show my Cloudinary storage and bandwidth usage
Set up
Every client connects to asset-management.mcp.cloudinary.com, and Cloudinary asks you to sign in the first time. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport http cloudinary https://asset-management.mcp.cloudinary.com/mcp- Start Claude Code, type
/mcp, pick cloudinary and choose Authenticate. A browser window opens for the Cloudinary sign-in.
Add --scope user to make it available in every project, not just this one.
Claude Desktop
- Open Customize → Connectors, click + Add, then Add custom connector.
- Name it Cloudinary and paste this URL:
https://asset-management.mcp.cloudinary.com/mcp- Click Add, then Connect, and sign in when Cloudinary asks.
Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.
claude.ai
- Open the connector form on claude.ai. This button fills in the name and URL for you:
Add to claude.ai (opens in a new tab)
- Check that the URL reads
https://asset-management.mcp.cloudinary.com/mcpand click Add. - Click Connect and sign in when Cloudinary asks.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.
ChatGPT
- On chatgpt.com, go to Plugins, select +, then Add custom MCP server.
- Enter a name for the server.
- Under Connection, paste
https://asset-management.mcp.cloudinary.com/mcpas the server URL, then for authentication choose OAuth. ChatGPT sends you to Cloudinary to sign in. - Check I understand and want to continue, then select Create as a plugin.
Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"cloudinary": {
"url": "https://asset-management.mcp.cloudinary.com/mcp"
}
}
}Cursor shows Needs authentication next to the server. Click the button beside it to sign in.
VS Code
Install in VS Code (opens in a new tab)
Or from a terminal:
code --add-mcp '{"name":"cloudinary","type":"http","url":"https://asset-management.mcp.cloudinary.com/mcp"}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"cloudinary": {
"type": "http",
"url": "https://asset-management.mcp.cloudinary.com/mcp"
}
}
}VS Code asks you to sign in the first time the server starts.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"cloudinary": {
"serverUrl": "https://asset-management.mcp.cloudinary.com/mcp"
}
}
}- Refresh the MCP server list in Cascade and sign in when asked.
Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.
Codex
codex mcp add cloudinary --url https://asset-management.mcp.cloudinary.com/mcp
codex mcp login cloudinaryOr edit ~/.codex/config.toml directly:
[mcp_servers.cloudinary]
url = "https://asset-management.mcp.cloudinary.com/mcp"Gemini CLI
gemini mcp add --transport http cloudinary https://asset-management.mcp.cloudinary.com/mcpThen, inside Gemini CLI, run /mcp auth cloudinary to sign in.
This adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.
{
"mcpServers": {
"cloudinary": {
"type": "http",
"url": "https://asset-management.mcp.cloudinary.com/mcp"
}
}
}Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.
Client only starts local servers? Bridge it with npx -y mcp-remote https://asset-management.mcp.cloudinary.com/mcp.
Embed
Show Cloudinary in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/cloudinary)<a href="https://mcp.tc/i/cloudinary"><img src="https://mcp.tc/i/cloudinary/badge.svg" alt="Cloudinary on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/cloudinary.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/cloudinary" title="Cloudinary on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/cloudinary.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Cloudinary card to your site.
Add the mcp.tc card for Cloudinary, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/cloudinary.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="cloudinary"><a href="https://mcp.tc/i/cloudinary">Cloudinary on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/cloudinary)
```
Reference: https://mcp.tc/embedChange history
We read the tool list in this server’s bundle manifest on GitHub every 3 hours and record what changes. Last read 18 Nov 2026, 05:31 UTC.
-
2 tools added.
Details, 15 Nov 2026, 11:56 UTC
Added 2
generate-video-from-imageCreate a video generation job Submits an image and prompt for video generation and returns a job you can poll for the result.
get-video-generation-jobPoll a video generation job Returns the current status of a generation job. When the status is `completed`, the response includes the generated video's asset details and delivery URL.
-
13 tools added.
Details, 5 Nov 2026, 11:51 UTC
Added 13
add-collection-assetsAdd assets to a collection Adds assets to an existing collection. The caller must be allowed to update the collection and view the assets.
create-collectionCreate a collection Creates a collection under the given product environment and makes the caller the owner.
delete-collectionDelete a collection Deletes a collection. The caller must be allowed to update the collection; the underlying assets are not modified or deleted.
get-collectionGet a collection Returns a single collection by its external ID.
get-collection-public-pageGet a public page Returns a single public page of a collection by its external ID.
list-collection-assetsList a collection's assets Returns the assets in a collection, newest first by default. For a `manual` collection, these are the assets that have been added to it; for a `dynamic` collection, they're the assets currently matching its filter expression. Only assets the caller has permission to view are included. Results are paginated: pass the returned `next_cursor` back to fetch the next page.
list-collection-public-pagesList a collection's public pages Returns the public pages (shareable links) that have been created for the collection.
list-collectionsList collections Returns the collections the caller may read, most-recently-updated first by default (`updated_at desc`). Results are paginated: pass the returned `next_cursor` back to fetch the next page.
publish-collectionPublish a collection Creates a shareable public page for the collection and returns its URL.
remove-collection-assetsRemove assets from a collection Removes the specified assets from an existing collection. The caller must be allowed to update the collection. Assets that are not in the collection are ignored, and the underlying assets are not modified or deleted.
unpublish-collection-public-pageUnpublish a collection's public page Deletes a collection's public page so it's no longer shareable. The collection and its assets aren't changed or deleted.
update-collectionUpdate a collection Updates a collection's name, description, and (for dynamic collections) configuration. Only the fields you include in the request are changed. The caller must be allowed to update the collection. A collection's type (manual/dynamic) is fixed at creation and can't be changed.
update-collection-public-pageUpdate a public page Updates the settings of a collection's public page and returns the updated page. Protecting a page (`protection_mode: email_otp`) requires the secured-sharing feature on your plan; otherwise the request fails with 403. Invalid protection settings fail with 400 and error code `invalid_protection_settings`, listing every problem found.
-
3 tools changed.
Details, 22 Oct 2026, 16:42 UTC
Changed 3
generate-imagedescriptionBeforeGenerate an image
Generate animage from a textprompt using AI models. The model is selected viatheoptional`model`object: 1. If `model.id`isprovided, use that exact model. 2. Else if `model.family` (+ optional `model.tier`)isprovided, resolve viathemodel registry;amissing tier defaultsto`standard`. 3. Else if `model.mode` is `auto`,theservice picksthemodelforthe request (optionally steered by `model.preference`). 4. Otherwise,usethe global default (nano-banana / premium, i.e. `nano-banana-2`).AfterGenerate an image from a text prompt Create any image from a text description with AI: photos, illustrations, logos, icons, product shots, banners, ads, social posts, concept art, mockups, and images with readable text. One call gives you the best image models — Nano Banana, GPT Image, FLUX, Ideogram, Recraft and more. Leave out `model` and a strong default is used. **Storage is optional.** Get the image at a temporary link without saving anything to your account, or keep it in your Media Library, ready to deliver, transform and optimize. **What you get back.** Each image comes with its URL, size, format and the model that made it, either in the response or, for longer jobs, from a background task you can check or be notified about. Each generation uses Image Generation credits. To edit, restyle or combine existing images, use image-to-image (`generate-image-from-images`) instead.
generate-image-from-imagesdescriptionBeforeGenerate an image from referenceimagesGenerate an imageguided byoneormore **reference images** — restyle,on-brand variants, characterconsistency,virtual try-on,edit/extend — steeredby`prompt`. Onlyedit-capable models areselectable here. The modelisselected viatheoptional `model` object, exactly like `text_to_image`, but IDs are restrictedtoedit models: 1. If `model.id` is provided, usethatexact edit model. 2. Else if `model.family` (+ optional `model.tier`) is provided, resolve to that family's edit model (e.g. `nano-banana` / `premium` → `nano-banana-2-edit`). 3. Else if `model.mode` is `auto`,theservice picks an edit modelforthe request (optionally steered by `model.preference`). 4. Otherwise, use the default edit model (`nano-banana-2-edit`). Each reference image is eitherastored managed asset (by `asset_id`, read-permission checked)oran external HTTPS `url`.AfterEdit or combine images with a text prompt Edit, restyle or combine existing images with AI, guided by a text prompt: replace a background, add or remove objects, apply a style, make on-brand variants, keep a character or product consistent across scenes, virtual try-on, or extend an image. Pass up to 4 reference images, each a public HTTPS `url` or an `asset_id` from the user's Cloudinary account, and refer to them in the prompt as `[1]`, `[2]`, …. For a local file, upload it first and reference it by its `asset_id`. Leave out `model` and a strong default edit model is used; only edit-capable models are accepted. **Storage is optional.** Get the image at a temporary link without saving anything to your account, or keep it in your Media Library. **What you get back.** Each image comes with its URL, size, format and the model that made it, either in the response or, for longer jobs, from a background task you can check or be notified about. Each generation uses Image Generation credits.
get-generation-taskdescriptionBeforeGet a generation task Getthe status of a generationtask.AfterCheck the status and result of a generation task Check on an image generation running in the background: whether it is pending, processing, completed or failed, and, once it has completed, the generated images with their URLs, size and format.
-
Tracking started: 29 tools.
FAQ
Can I paste mcp.tc/i/cloudinary into my MCP client?
No. mcp.tc links are pages, not server addresses. Connect with https://asset-management.mcp.cloudinary.com/mcp, so your client talks to Cloudinary directly. The sign-in token only works there anyway. The quick link is for sharing: it opens this page, with setup steps for every client.
Does Cloudinary need an API key or a sign-in?
Yes, you need a Cloudinary account. The first time your client connects, it opens Cloudinary’s sign-in page. The token goes straight to the server’s own URL, never through mcp.tc.
Is Cloudinary a remote or a local server?
Remote. Cloudinary hosts it at https://asset-management.mcp.cloudinary.com/mcp, and it speaks Streamable HTTP. There’s nothing to install.
What can Cloudinary do?
It has 44 tools, including upload-asset, asset-rename and generate-archive. You can upload images, videos and raw files from paths, URLs or data URIs, search assets with queries or by visual similarity and add, remove or replace tags and metadata on many assets.
Which clients can use it?
Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.
Does mcp.tc track changes to Cloudinary?
Yes. We follow the tool list in Cloudinary’s bundle manifest, and its History tab shows each change we find, plus new versions and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read Cloudinary’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with Cloudinary. This page was built from Cloudinary’s public metadata, last checked on 17 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.